Preventing I/O starvation on MD1000s triggered by a failed disk.

Tim Small tim at seoss.co.uk
Tue Aug 24 06:38:04 CDT 2010


On 24/08/10 05:33, Bond Masuda wrote:
> I run this once a month on all my RAID-5 arrays that use 500GB or larger
> disks. It was also recommended to me by a Dell technician.
>
> However, what I actually do in practice aside, I sometimes wonder if
> this is a good thing or not? If I recall correctly, an error occurs
> about every 12TB read per disk. Every time I do a consistency check, the
> entire array is read and so it would seem that I'm increasing my chances
> of the eventual and inevitable encounter with a URE? On the other hand,
> if there is a URE, I would rather find out about it before the RAID-5
> becomes degraded so I can actually recover.
>    

I'm assuming that by URE you mean an unreadable sector?

I believe the software RAID in Debian does a consistency check once per 
month by default.  I'm surprised that the PERCs don't schedule these by 
default...  In my experience with software RAID, a read check is a good 
thing since:

. The disks may spot failing (but not yet unrecoverable) sectors and 
transparently correct them using their ECC mechanisms.
. The RAID algorithms can recover the data and restore consistency where 
sectors have become unreadable (the drives then reallocate the sectors 
in question if necessary).


> Either way, having encountered numerous UREs now, and often during a
> degraded array rebuild, I think the more effective solution is simply to
> go with RAID-6 rather than relying on regular consistency checks.
>    


We usually run RAID6 on arrays with more than 4 drives...

Cheers,

Tim.


-- 
South East Open Source Solutions Limited
Registered in England and Wales with company number 06134732.
Registered Office: 2 Powell Gardens, Redhill, Surrey, RH1 1TQ
VAT number: 900 6633 53  http://seoss.co.uk/ +44-(0)1273-808309



More information about the Linux-PowerEdge mailing list